A framework for computing upper bounds in passive learning settings
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913871771467776 |
|---|---|
| author | Bordais, Benjamin Neider, Daniel |
| author_facet | Bordais, Benjamin Neider, Daniel |
| contents | The task of inferring logical formulas from examples has garnered significant attention as a means to assist engineers in creating formal specifications used in the design, synthesis, and verification of computing systems. Among various approaches, enumeration algorithms have emerged as some of the most effective techniques for this task. These algorithms employ advanced strategies to systematically enumerate candidate formulas while minimizing redundancies by avoiding the generation of syntactically different but semantically equivalent formulas. However, a notable drawback is that these algorithms typically do not provide guarantees of termination, which poses challenges for their use in real-world applications.
This paper develops an abstract framework to bound the size of possible solutions for a logic inference task, thereby providing a termination guarantee for enumeration algorithms through the introduction of a sufficient stopping criterion. The proposed framework is designed with flexibility in mind and is applicable to a broad spectrum of practically relevant logical formalisms, including Modal Logic, Linear Temporal Logic, Computation Tree Logic, Alternating-time Temporal Logic, and even selected inference task for finite automata. In addition, our approach enabled us to develop a new class of algorithms that enumerate over the semantics of formulas rather than their syntactic representations, offering new possibilities for reducing redundancy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03517 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A framework for computing upper bounds in passive learning settings Bordais, Benjamin Neider, Daniel Logic in Computer Science The task of inferring logical formulas from examples has garnered significant attention as a means to assist engineers in creating formal specifications used in the design, synthesis, and verification of computing systems. Among various approaches, enumeration algorithms have emerged as some of the most effective techniques for this task. These algorithms employ advanced strategies to systematically enumerate candidate formulas while minimizing redundancies by avoiding the generation of syntactically different but semantically equivalent formulas. However, a notable drawback is that these algorithms typically do not provide guarantees of termination, which poses challenges for their use in real-world applications. This paper develops an abstract framework to bound the size of possible solutions for a logic inference task, thereby providing a termination guarantee for enumeration algorithms through the introduction of a sufficient stopping criterion. The proposed framework is designed with flexibility in mind and is applicable to a broad spectrum of practically relevant logical formalisms, including Modal Logic, Linear Temporal Logic, Computation Tree Logic, Alternating-time Temporal Logic, and even selected inference task for finite automata. In addition, our approach enabled us to develop a new class of algorithms that enumerate over the semantics of formulas rather than their syntactic representations, offering new possibilities for reducing redundancy. |
| title | A framework for computing upper bounds in passive learning settings |
| topic | Logic in Computer Science |
| url | https://arxiv.org/abs/2504.03517 |